Skip to main content
Log in

Application of SVM and its Improved Model in Image Segmentation

  • Published:
Mobile Networks and Applications Aims and scope Submit manuscript

Abstract

In the research and application of images, people are often only interested in the foreground or specific area of the image, so it is necessary to extract the specific area from the image, and image segmentation technology is the key to solving this problem. Aiming at the complex background and the color image with unclear target contour as the target image to be segmented, this paper first uses the texture and color of the image as the feature vector, and proposes an image segmentation algorithm based on SVM. The experimental results show that the segmentation accuracy is 91.23%. Secondly, in order to improve the accuracy of segmentation, the SVM algorithm is improved. The improved SVM algorithm is based on the grid search method to optimize the parameters C and g in the SVM. At the same time, the HIS color channel is added to the feature vector to obtain more Excellent SVM image segmentation model. Finally, the color image segmentation is verified and compared with the standard SVM algorithm. The experimental results show that the accuracy rate of the improved SVM algorithm reaches 97.263%, which improves the segmentation efficiency. It is verified that the improved model proposed in this paper can effectively segment complex color images.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

References

  1. He KM, Sun J, Tang XO (2013) Guided Image Filtering. IEEE Transactions on Pattern Analysis & Machine Intelligence. 35(6), 1397-1409

  2. Qian H, Ashley J, Niblack W et al (2013) Yanker "query by image and video content: the qbic system. 12(1), 232-232

  3. Goetz MP, Callstrom MR, Charboneau JW et al. (2016) Percutaneous Image-Guided Radiofrequency Ablation of Painful Metastases Involving Bone: A Multicenter Study. 224(1), 87

  4. Zhang F, Fan H (2014) Research on medical image segmentation based on fuzzy C-means clustering algorithm. Computer Engineering and Applications. 50(4), 144-151

  5. Zhu R, Li JY (2015). Image Segmentation Research Based on Improved Fcm Algorithm. Microelectronics & Computer, PP. 151-153

  6. Alham NK, Li MZ, Liu Y et al.: A MapReduce-based distributed SVM ensemble for scalable image classification and annotation. Computers & Mathematics with Applications. 66(10):1920-1934 (2013)

  7. Robertas DV (2010) Optimization of SVM parameters for recognition of regulatory DNA sequences. 18(2):339-353

  8. Zhai Y, Liu L, Shu YU (2015) Utilization of nonlinear SVM with grid-search method for identification of piping occurring probability in embankment engineering. 46(4):1497-1503

  9. Chen YF, Yun T, Zhou Y et al. (2014) Texture Image Segmentation Based on PSO Optimising SVM. Computer Applications and Software. 31(4)

  10. Feng Z, Chen YF, Zhou Y et al. (2014) Parameter optimization and application of SVM based on improved NCSPSO and AFSA. Journal of Jiangsu University of Science and Technology (Natural Science Edition), PP. 402

  11. Wang M (2019) Ultrasonic image segmentation based on improved support vector machine algorithm. Journal of Biomedical Engineering Research, 38(2)

  12. Antonin L, Cécile LP, Terrier P et al (2013) Epithelioid Sarcoma: Need for a Multimodal Approach to Maximize the Chances of Curative Conservative Treatment. Annals of Surgical Oncology 21(1):269

    Google Scholar 

  13. Wu D, Hu S, Hu LZ et al (2017) FSVM color image segmentation based on visual attention and improved membership. Computer system application 26(1):141–146

    MathSciNet  Google Scholar 

  14. Zhao SN, Wang WJ (2017) Image segmentation algorithm combining SVM and fast mean shift. Small microcomputer system 38(07):1614–1618

    Google Scholar 

  15. Zhao JD, Wu HQ, Chen LL, et al. (2017) Road Surface State Recognition Based on SVM Optimization and Image Segmentation Processing. Journal of Advanced Transportation

  16. Masood A, Adel AJ (2015) Differential evolution based advised SVM for histopathalogical image analysis for skin cancer detection. Conference proceedings Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference

  17. Chen CP, Zou L, Wang W (2013) Underwater Image Transition Region Extraction and Segmentation Based on SVM. Applied Mechanics and Materials, 2658

  18. Antonin L, Cécile LP, Philippe T et al (2013) Epithelioid Sarcoma: Need for a Multimodal Approach to Maximize the Chances of Curative Conservative Treatment. Annals of Surgical Oncology 21(1):269

    Google Scholar 

  19. Li X, Cai J, Zuo HF et al (2018) Joint optimization of sampling interval and control for condition-based maintenance using availability maximization criterion. Journal of Systems Engineering and Electronics 29(1):203–215

    Article  Google Scholar 

  20. Bougleux S, Peyré G, Cohen L (2011) Non-local regularization of inverse problems. Inverse Problems & Imaging 5(2):511–530

    Article  MathSciNet  Google Scholar 

  21. Grazia FS, Sara B, Claudia C et al. (2017) Normative Data for the Hayling and Brixton Tests in an Italian Population. Archives of Clinical Neuropsychology. 33(Pt A):11

  22. Zhang L, Shao ZF (2014) Hyperspectral remote sensing image classification based on improved OIF and SVM algorithm. 9263(13):92632-92632

  23. Srinivasan V, Rajenderan G, Kuzhali JV et al. (2013) Fuzzy fast classification algorithm with hybrid of ID3 and SVM. 24(3):555-561

  24. Betensky RA, Finkelstein DM (1999) A non-parametric maximum likelihood estimator for bivariate interval censored data. Statistics in Medicine. 18(22):3089–3100

    Article  Google Scholar 

  25. Li XB, Gong X, Peng XN et al (2013) SSiCP: a new SVM based Recursive Feature Elimination Algorithm for Multiclass Cancer Classification. Bio-medical materials and engineering. 23:S1027–S1038

    Google Scholar 

  26. Tao X, Cao P, Song S et al (2013) The SVM classification algorithm based on semi-supervised Gauss mixture model kernel. Information & Control 42(1):18–26

    Google Scholar 

  27. Rajendran S, Kalpana B (2013) Improvised Admissible Kernel Function for Support Vector Machines in Banach Space for Multiclass Data. 11(2)

  28. Laskey WK, Holmes DR (2015) Kern M J. Image quality assessment: A timely look. 46(2):125-126

  29. Alexander D, Zikic D, Zhang J et al. (2014) Image Quality Transfer via Random Forest Regression: Applications in Diffusion MRI. 17(3):225-232

  30. Dong HB, Li YD, Kang Y et al (2015) Comparison of image quality and application values on different field-of-view diffusion-weighted imaging of breast cancer. Acta Radiologica 14(1):990–997

    Google Scholar 

  31. Ghosh S, Wang YZ (2015) Feature Import Vector Machine: A General Classifier with Flexible Feature Selection. Statistical Analysis & Data Mining. 8(1)

  32. Nguyen VD, Nguyen DT, Nguyen TD et al (2015) Filter-based feature selection and support vector machine for false positive reduction in computer-aided mass detection in mammograms. Proceedings of SPIE - The International Society for Optical Engineering 9445(4):479–487

    Google Scholar 

  33. Xu XX, Liang JZ (2015) Face Recognition Method Based on Gabor Wavelet and Supervised 2DNPE. Journal of Chinese Computer Systems. 37(14):68–67

    Google Scholar 

  34. Wang R, Wang GU, Chen Z et al (2014) A palm vein identification system based on Gabor wavelet features. Neural Computing & Applications 24(1):161–168

    Article  Google Scholar 

  35. Moacir P, Nazaré TS, Gabriela S (2015) Thumé. Image quantization as a dimensionality reduction procedure in color and texture feature extraction. Neurocomputing. 173(P2):385-396

  36. Mistry YD, Ingole DT (2014) Content-based image retrieval using DWT based feature extraction and texture, shape and color features. 3(11)

  37. Min CB, Zhang JJ, Chang BL et al (2013) An Evaluation Criterion of Salient Target Segmentation without Prior Knowledge in Infrared Image. Pattern Recognition & Artificial Intelligence 26(12):1106–1114

    Google Scholar 

  38. Song EM, Qian YJ, Liu H et al. (2017) A target-oriented segmentation method for specific tissues in MRI images of the brain. Multimedia Tools & Applications, PP. 1-17

  39. Zhao T, Ruan D (2016) TH‐CD‐206‐06: Regularized Composite Shape Prior Encoding Shape Relevance in Variational Image Segmentation. Medical Physics. 43

  40. Gong YN, Hua JX, Huang XB (2001) Regular Texture Defect Detection Based onMatched Gabor Filters. Journal of Imag e and Graphics, PP.14-18

  41. A-Iyeh E, Peters JF (2015) Gini index-based digital image complementing in the study of medical images. Intelligent Decision Technologies. 9(2):209–218

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported by the National Natural Science Foundation of China (No. 51674121).

Author information

Authors and Affiliations

Authors

Corresponding authors

Correspondence to Yunjie Bai, Huixiang Liu or Tao Xue.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yang, A., Bai, Y., Liu, H. et al. Application of SVM and its Improved Model in Image Segmentation. Mobile Netw Appl 27, 851–861 (2022). https://doi.org/10.1007/s11036-021-01817-2

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11036-021-01817-2

Keywords

Navigation